Leveraging SO(3)-steerable convolutions for pose-robust semantic segmentation in 3D medical data
- URL: http://arxiv.org/abs/2303.00351v3
- Date: Fri, 17 May 2024 14:16:26 GMT
- Title: Leveraging SO(3)-steerable convolutions for pose-robust semantic segmentation in 3D medical data
- Authors: Ivan Diaz, Mario Geiger, Richard Iain McKinley,
- Abstract summary: We present a new family of segmentation networks that use equivariant voxel convolutions based on spherical harmonics.
These networks are robust to data poses not seen during training, and do not require rotation-based data augmentation during training.
We demonstrate improved segmentation performance in MRI brain tumor and healthy brain structure segmentation tasks.
- Score: 2.207533492015563
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Convolutional neural networks (CNNs) allow for parameter sharing and translational equivariance by using convolutional kernels in their linear layers. By restricting these kernels to be SO(3)-steerable, CNNs can further improve parameter sharing. These rotationally-equivariant convolutional layers have several advantages over standard convolutional layers, including increased robustness to unseen poses, smaller network size, and improved sample efficiency. Despite this, most segmentation networks used in medical image analysis continue to rely on standard convolutional kernels. In this paper, we present a new family of segmentation networks that use equivariant voxel convolutions based on spherical harmonics. These networks are robust to data poses not seen during training, and do not require rotation-based data augmentation during training. In addition, we demonstrate improved segmentation performance in MRI brain tumor and healthy brain structure segmentation tasks, with enhanced robustness to reduced amounts of training data and improved parameter efficiency. Code to reproduce our results, and to implement the equivariant segmentation networks for other tasks is available at http://github.com/SCAN-NRAD/e3nn_Unet
Related papers
- Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware [78.17783007774295]
This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval.
A novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed.
The converted SNNs achieve almost five-fold power efficiency at moderate performance loss compared to the original CNNs.
arXiv Detail & Related papers (2024-12-05T09:41:33Z) - Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks [79.16635054977068]
We present a new class of equivariant neural networks, dubbed Lattice-Equivariant Neural Networks (LENNs)
Our approach develops within a recently introduced framework aimed at learning neural network-based surrogate models Lattice Boltzmann collision operators.
Our work opens towards practical utilization of machine learning-augmented Lattice Boltzmann CFD in real-world simulations.
arXiv Detail & Related papers (2024-05-22T17:23:15Z) - Efficient 3D affinely equivariant CNNs with adaptive fusion of augmented spherical Fourier-Bessel bases [0.36122488107441414]
Filter-decomposition-based group equivariant convolutional neural networks (CNNs) have shown promising stability and data efficiency for 3D image feature extraction.
This paper presents an efficient non- parameter-sharing continuous 3D affine group equivariant neural network for volumetric images.
arXiv Detail & Related papers (2024-02-26T18:51:15Z) - Heterogenous Memory Augmented Neural Networks [84.29338268789684]
We introduce a novel heterogeneous memory augmentation approach for neural networks.
By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead.
We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
arXiv Detail & Related papers (2023-10-17T01:05:28Z) - Regular SE(3) Group Convolutions for Volumetric Medical Image Analysis [10.406659081400354]
We devise a SE(3) group convolution kernel separated into a continuous SO(3) (rotation) kernel and a spatial kernel.
Our approach achieves up to a 16.5% gain in accuracy over regular CNNs.
arXiv Detail & Related papers (2023-06-24T13:29:54Z) - Moving Frame Net: SE(3)-Equivariant Network for Volumes [0.0]
A rotation and translation equivariant neural network for image data was proposed based on the moving frames approach.
We significantly improve that approach by reducing the computation of moving frames to only one, at the input stage.
Our trained model overperforms the benchmarks in the medical volume classification of most of the tested datasets from MedMNIST3D.
arXiv Detail & Related papers (2022-11-07T10:25:38Z) - GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction [50.248694764703714]
Unrolled neural networks have recently achieved state-of-the-art accelerated MRI reconstruction.
These networks unroll iterative optimization algorithms by alternating between physics-based consistency and neural-network based regularization.
We propose Greedy LEarning for Accelerated MRI reconstruction, an efficient training strategy for high-dimensional imaging settings.
arXiv Detail & Related papers (2022-07-18T06:01:29Z) - Two-Stream Graph Convolutional Network for Intra-oral Scanner Image
Segmentation [133.02190910009384]
We propose a two-stream graph convolutional network (i.e., TSGCN) to handle inter-view confusion between different raw attributes.
Our TSGCN significantly outperforms state-of-the-art methods in 3D tooth (surface) segmentation.
arXiv Detail & Related papers (2022-04-19T10:41:09Z) - Invertible Residual Network with Regularization for Effective Medical
Image Segmentation [2.76240219662896]
Invertible neural networks have been applied to significantly reduce activation memory footprint when training neural networks with backpropagation.
We propose two versions of the invertible Residual Network, namely Partially Invertible Residual Network (Partially-InvRes) and Fully Invertible Residual Network (Fully-InvRes)
Our results indicate that by using partially/fully invertible networks as the central workhorse in volumetric segmentation, we not only reduce memory overhead but also achieve compatible segmentation performance compared against the non-invertible 3D Unet.
arXiv Detail & Related papers (2021-03-16T13:19:59Z) - CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image
Segmentation [95.51455777713092]
Convolutional neural networks (CNNs) have been the de facto standard for nowadays 3D medical image segmentation.
We propose a novel framework that efficiently bridges a bf Convolutional neural network and a bf Transformer bf (CoTr) for accurate 3D medical image segmentation.
arXiv Detail & Related papers (2021-03-04T13:34:22Z) - HIVE-Net: Centerline-Aware HIerarchical View-Ensemble Convolutional
Network for Mitochondria Segmentation in EM Images [3.1498833540989413]
We introduce a novel hierarchical view-ensemble convolution (HVEC) to learn 3D spatial contexts using more efficient 2D convolutions.
The proposed method performs favorably against the state-of-the-art methods in accuracy and visual quality but with a greatly reduced model size.
arXiv Detail & Related papers (2021-01-08T06:56:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.